Scribd
Upload
4 views

CS417-Course outline

CS 417 is a course on intelligent systems and neural networks, focusing on artificial intelligence techniques and their applications. It covers topics such as artificial neural networks, genetic algorithms, and recommender systems, with both theoretical and practical components. The course includes lectures, assignments, a midterm, and a final project, with resources available on Moodle.

Uploaded by

mbielawski21
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

CS417-Course outline

CS 417 is a course on intelligent systems and neural networks, focusing on artificial intelligence techniques and their applications. It covers topics such as artificial neural networks, genetic algorithms, and recommender systems, with both theoretical and practical components. The course includes lectures, assignments, a midterm, and a final project, with resources available on Moodle.

Uploaded by

mbielawski21
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Course outline CS 417 – Special Topics in Computer Science Fall 2023

Computer Science Department


CS 417 – Special Topics in Computer Applications
“Intelligent systems and neural networks”

Course outline
Fall 2023

Professor:
Dr. Rachid Hedjam
Email: [email protected]
Office: Bishop’s University, NIC 203
Office hours: Online via Microsoft Teams

Schedule:
Lecture: In-person

Description

Objective: To be familiar with some artificial intelligence techniques focusing on building


intelligent systems.
Content The course introduces students to the theoretical and practical knowledge of
different models of intelligent systems including bio-inspired systems (genetic
algorithms, swarm optimization), artificial neural networks, recommendation
systems, Bayesian networks. The course is theoretical and practical. Students will
be exposed to solving different types of artificial intelligence applications mainly
in search, inference and learning.
Credits 3
Organization Three hours of lecture per week
Three/four hours of personal work per week.
1 Topics

The content of this course is the following:

Introduction
• Course overview.
• What is Artificial Intelligence?
• Challenges and Ethics of AI.
• Some applications of AI.

1
Course outline CS 417 – Special Topics in Computer Science Fall 2023
o
Combinatorial search and optimization
o
Learning
o
Reasoning
o
Recommendation
Artificial Neural Networks (ANN)
• Biological Neuron vs Artificial Neuron.
• Artificial neural nets.
• Basic principle of ANN.
• Applications of ANN (pattern/data classification)
Single layer perceptron
• Theory of perceptron
• Perceptron learning rule
• Perceptron in practice (Python/Sklearn)
Multi-layer perceptron (MLP)
• Representation
• MLP for binary classification
• MLP for multiclass classification
• Activation functions
• Forward propagation
• Demo in Python/Sklearn
Multi-layer perceptron (MLP)
• Loss functions (MSE, Cross Entropy)
• Optimization with Gradient descent method (SGD, Adam)
• Backpropagation
• Demo in Python/Sklearn
Multi-layer perceptron (MLP)
• Application of MLP for image classification
• Application of MLP for Network intrusion detection
Cooperative intelligence and optimization
• Theory of Particle swarm optimization (PSO)
• Applications of PSO for search/optimization problems
o Demo (Python): Knapsack/Traveling salesman problems.
o Demo (Python/Sklearn): e.g., optimization of MLP
Genetic Algorithms (GA)
• Theory of GA
• Applications of GA for search/optimization problems
o Demo (Python/Sklearn): Knapsack/Traveling salesman problems.
o Demo (Python/Sklearn): e.g., optimization of MLP
Recommender systems (RS)
• What is RS?
• Applications of RS
• Content-based RS
• Collaborative filtering-based RS
• Demo (Python): E-commerce, Media.
Reasoning under Uncertainty
• Probabilities
• Conditional independence
• Introduction to Bayesian networks

2
Course outline CS 417 – Special Topics in Computer Science Fall 2023
• D-separation
• Demo (Python): Medical diagnosis
2 Organization

2.1 Teaching method

A week includes three hours of lessons. The presentation of the courses will be done using slides
(available on Moodle) and/or on board. Throughout the semester, the student will implement
the concepts seen in class through four assignments. The course includes a midterm exam and a
final exam.

Evaluation
Items Date Out Due Date Weights
HW 1 WEEK 3 WEEK 5 5%
HW 2 WEEK 5 WEEK 7 5%
HW 3 WEEK 7 WEEK 9 10 %
HW 4 WEEK 9 WEEK 11 10 %
Midterm 1 WEEK 7/8 20 %
Quizzes TBD 10 %
FINAL/project TBD 40%
Unless otherwise stated, the assignments can be done individually. Special instructions will be given for
each assignment. The submission of assignment must be performed through Moodle. Subjects will be
available on Moodle. The delivery of work is done before midnight of the due day. Failure to submit an
assignment before the deadline will result in a penalty of 10% per day late, including Saturday and
Sunday.
No assignment can be submitted by email.
Plagiarized or undelivered assignment will be automatically attributed the grade zero.
2.2 Course Material

Some course’s slides will be available on Moodle.

2.3 Bibliography

1) Nielsen MA. Neural networks and deep learning. San Francisco, CA, USA: Determination press;
2015 Sep 25
2) Aggarwal CC. Neural networks and deep learning. Springer. 2018 Sep;10(978):3.
3) Luke S. Essentials of metaheuristics. Raleigh: Lulu; 2013
4) Wirsansky E. Hands-on genetic algorithms with Python: applying genetic algorithms to solve real-
world deep learning and artificial intelligence problems. Packt Publishing Ltd; 2020 Jan 31.
5) Aggarwal CC. Recommender systems. Cham: Springer International Publishing; 2016
6) Russell SJ. Artificial intelligence a modern approach. Pearson Education, Inc.; 2010.

You might also like